Fault Detection in Electricity Transmission Lines: A Comparative Analysis of Ensemble Machine Learning and Convolutional Neural Network Methods

As the number of transmission lines increases to meet the increasing load demand in electric power systems, the number of faults increases in parallel. Faults caused by external environmental factors can pose a serious threat to these lines and cause damage to the system. Therefore, fast and accurate detection of faults in transmission lines is of vital importance. In this study, an artificial neural network-based model is developed to detect faults in transmission lines. Firstly, various machine learning algorithms such as Bagging, AdaBoost and Gradient Boosting Classifier are used for fault detection and all models are put through training and testing processes. According to the test results, the Gradient Boosting Classifier algorithm showed the highest success. However, in order to achieve higher accuracy, a Convolutional Neural Network (CNN), a deep learning-based model, was proposed in this study. The proposed model achieved an accuracy rate of 99.73%, which is better than that of the machine learning algorithms. These results demonstrate that the neural network-based model plays an important role in ensuring the reliability and continuity of power systems by effectively detecting transmission line faults.